Paper Info
Title
Dense Segmentation-Aware Descriptors
Abstract
In this work we exploit segmentation to construct appearance descriptors that can robustly deal with occlusion and background changes. For this, we downplay measurements coming from areas that are unlikely to belong to the same region as the descriptor's center, as suggested by soft segmentation masks. Our treatment is applicable to any image point, i.e. dense, and its computational overhead is in the order of a few seconds. We integrate this idea with Dense SIFT, and also with Dense Scale and Rotation Invariant Descriptors (SID), delivering descriptors that are densely computable, invariant to scaling and rotation, and robust to background changes. We apply our approach to standard benchmarks on large displacement motion estimation using SIFT-flow and wide-baseline stereo, systematically demonstrating that the introduction of segmentation yields clear improvements.
Year
DOI
Venue
2013
10.1109/CVPR.2013.372
Computer Vision and Pattern Recognition
Keywords
Field
DocType
image segmentation,image sequences,motion estimation,stereo image processing,transforms,SID,background change robustness,computational overhead,dense SIFT-flow,dense scale-and-rotation invariant descriptors,dense segmentation-aware appearance descriptors,displacement motion estimation,image point,occlusion changes,standard benchmarks,wide-baseline stereo,appearance descriptors,matching,segmentation,stereo
Scale-invariant feature transform,Computer vision,Scale-space segmentation,Pattern recognition,Computer science,Segmentation,Image segmentation,Feature extraction,Invariant (mathematics),Artificial intelligence,Motion estimation,Optical flow
Conference
Volume
Issue
ISSN
2013
1
1063-6919
Citations 
PageRank 
References 
25
0.90
37
Authors
4
Name
Order
Citations
PageRank
Eduard Trulls131811.07
Iasonas Kokkinos2252888.22
Alberto Sanfeliu31757162.98
Francesc Moreno-Noguer4164793.46